I can not use  downsamaple.max_pool_2d, how it is called now? 
theano.tensor.signal.pool.pool_2d () or theano.tensor.signal.pool.
max_pool_2d_same_size()

regards. 

El martes, 1 de marzo de 2016, 3:02:48 (UTC+1), Michael Klachko escribió:
>
> To answer my own question, the new code for average pooling is about 4 
> times faster. 
>
>
>
> On Friday, February 26, 2016 at 2:05:10 PM UTC-8, Michael Klachko wrote:
>>
>> Thanks! Actually, it's theano.tensor.signal.pool. 
>> Previously, to implement averaging pooling operation, I used the 
>> following code:
>>
>>             pooled_out = TSN.images2neibs(ten4=conv_out, neib_shape=
>> poolsize, mode='ignore_borders').mean(axis=-1)
>>             new_shape = T.cast(T.join(0, conv_out.shape[:-2],
>>                                            T.as_tensor([conv_out.shape[2
>> ]/poolsize[0]]),
>>                                            T.as_tensor([conv_out.shape[3
>> ]/poolsize[1]])), 'int64')
>>             pooled_out = T.reshape(pooled_out, new_shape, ndim=4) 
>>
>> Where TSN is theano.sandbox.neighbours. I wonder if there's any speed 
>> advantage to replace this code with:
>>
>> pooled_out = pool.pool_2d(conv_out, ds=poolsize, ignore_border=True, 
>> st=None, padding=(0,0), mode=pooltype)
>>
>>
>>
>> On Friday, February 26, 2016 at 6:06:12 AM UTC-8, nouiz wrote:
>>>
>>> theano.tensor.nnet.pool
>>>
>>> Fred
>>>
>>> On Thu, Feb 25, 2016 at 7:56 PM, Michael Klachko <[email protected]> 
>>> wrote:
>>>
>>>> I'm running the latest dev version, where do I find this new 'pool' 
>>>> module?
>>>>
>>>> -- 
>>>>
>>>> --- 
>>>> You received this message because you are subscribed to the Google 
>>>> Groups "theano-users" group.
>>>> To unsubscribe from this group and stop receiving emails from it, send 
>>>> an email to [email protected].
>>>> For more options, visit https://groups.google.com/d/optout.
>>>>
>>>
>>>

-- 

--- 
You received this message because you are subscribed to the Google Groups 
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to